airunway-aks-setup
microsoft/azure-skills
Set up AI Runway on AKS from bare cluster to running model in 6 steps.
What is airunway-aks-setup?
This skill guides you through a complete AI Runway deployment on an existing AKS cluster, including controller installation, GPU assessment, inference provider setup, and first model deployment. Use it when you need to onboard a cluster for AI model serving or resume a partially-complete setup.
- Verify cluster connectivity, node inventory, and GPU hardware detection
- Install AI Runway controller and custom resource definitions (CRDs)
- Assess GPU models and identify dtype/attention constraints for inference
- Recommend and install an inference provider (KAITO, Dynamo, or KubeRay)
- Deploy and verify a first AI model on the cluster
- Report cluster health and readiness at each step
How to install airunway-aks-setup
npx skills add https://github.com/microsoft/azure-skills --skill airunway-aks-setup- An existing AKS cluster (provision via azure-kubernetes skill if needed)
- kubectl CLI configured with access to the cluster
- make and curl CLI tools available locally
- Understanding of GPU costs (A100-80GB: $3–5+/hr)
How to use airunway-aks-setup
- 1.Run the skill and confirm you have an existing AKS cluster; if not, hand off to azure-kubernetes first
- 2.Follow step 1 to verify cluster connectivity, node inventory, and GPU detection
- 3.Follow step 2 to install the AI Runway controller and CRDs
- 4.Follow step 3 to assess GPU hardware and identify constraints
- 5.Follow step 4 to select and install an inference provider (KAITO, Dynamo, or KubeRay)
- 6.Follow step 5 to deploy and verify your first AI model
- 7.Review step 6 summary and next steps; use skip-to-step N to resume from any earlier step
Use cases
- Onboarding a new AKS cluster for AI model serving with GPU inference
- Installing AI Runway controller and dependencies from scratch
- Assessing GPU hardware compatibility before deploying large language models
- Choosing between KAITO, Dynamo, and KubeRay inference providers for your workload
- Resuming a partially-complete AI Runway setup from a specific step
- DevOps engineers setting up Kubernetes infrastructure for AI workloads
- ML engineers deploying models to AKS for the first time
- Platform teams onboarding AI Runway across multiple clusters
- Users resuming interrupted or failed AI Runway deployments
airunway-aks-setup FAQ
Yes. This skill assumes you already have a running AKS cluster. If you don't, use the azure-kubernetes skill to provision one first, then return here.
CPU-only inference is possible but slower. The skill will detect this and guide you; for production AI workloads, GPU nodes are strongly recommended.
Yes. Provide skip-to-step N (e.g., skip-to-step 4) to resume from a specific phase; the skill assumes prior steps are complete.
The skill recommends and installs KAITO, Dynamo, or KubeRay based on your hardware and use case.
The skill reports cluster state and errors at each step. For detailed remediation, see the troubleshooting.md reference (e.g., CrashLoopBackOff, GPU scheduling failures, dtype errors).
Full instructions (SKILL.md)
Source of truth, from microsoft/azure-skills.
name: airunway-aks-setup description: "Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster", "install AI Runway", "airunway setup", "deploy model to AKS", "GPU inference on AKS", "KAITO setup on AKS", "run LLM on AKS", "vLLM on AKS", "set up model serving on AKS", "AI Runway controller"." license: MIT metadata: author: Microsoft version: "1.1.1" argument-hint: "[skip-to-step N]"
AI Runway AKS Setup
This skill walks users from a bare Kubernetes cluster to a running AI model deployment. Follow each step in sequence unless the user provides skip-to-step N to resume from a specific phase.
Cost awareness: GPU node pools incur significant compute charges (A100-80GB can cost $3–5+/hr). Confirm the user understands cost implications before provisioning GPU resources.
Prerequisites
This skill assumes an AKS cluster already exists. If the user does not have a cluster, hand off to the azure-kubernetes skill first to provision one (with a GPU node pool unless CPU-only inference is acceptable), then return here.
Quick Reference
| Property | Value |
|---|---|
| Best for | End-to-end AI Runway onboarding on AKS |
| CLI tools | kubectl, make, curl |
| MCP tools | None |
| Related skills | azure-kubernetes (cluster setup), azure-diagnostics (troubleshooting) |
When to Use This Skill
Use this skill when the user wants to:
- Set up AI Runway on an existing AKS cluster from scratch
- Install the AI Runway controller and CRDs
- Assess GPU hardware compatibility for model deployment
- Choose and install an inference provider (KAITO, Dynamo, KubeRay)
- Deploy their first AI model to AKS via AI Runway
- Resume a partially-complete AI Runway setup from a specific step
MCP Tools
This skill uses no MCP tools. All cluster operations are performed directly via kubectl and make.
Rules
- Execute steps in sequence — load the reference for each step as you reach it
- Report cluster state at each step: ✓ healthy, ✗ missing/failed
- Ask for user confirmation before any install or deployment action
- If a step is already complete, report status and skip to the next step
- If the user provides
skip-to-step N, start at step N; assume prior steps are complete
Steps
| # | Step | Reference |
|---|---|---|
| 1 | Cluster Verification — context check, node inventory, GPU detection | step-1-verify.md |
| 2 | Controller Installation — CRD + controller deployment | step-2-controller.md |
| 3 | GPU Assessment — detect GPU models, flag dtype/attention constraints | step-3-gpu.md |
| 4 | Provider Setup — recommend and install inference provider | step-4-provider.md |
| 5 | First Deployment — pick a model, deploy, verify Ready | step-5-deploy.md |
| 6 | Summary — recap, smoke test, next steps | step-6-summary.md |
Error Handling
| Error / Symptom | Likely Cause | Remediation |
|---|---|---|
| No kubeconfig context | Not connected to a cluster | Run az aks get-credentials or equivalent |
| Controller in CrashLoopBackOff | Config or RBAC issue | kubectl logs -n airunway-system -l control-plane=controller-manager --previous |
| Provider not ready | Image pull or RBAC issue | kubectl logs <pod-name> -n <namespace> for the provider pod |
| ModelDeployment stuck in Pending | GPU scheduling failure or provider not ready | kubectl describe modeldeployment <name> -n <namespace> events |
bfloat16 errors at inference | T4 or V100 lacks bfloat16 support | Add --dtype float16 to serving args |
For full error handling and rollback procedures, see troubleshooting.md.
Related skills
More from microsoft/azure-skills and the wider catalog.
